We provide a novel characterization of augmented balancing weights, also known as automatic debiased machine learning (AutoDML). These popular "doubly robust" or "de-biased machine learning estimators" combine outcome modeling with balancing weights -- weights that achieve covariate balance directly in lieu of estimating and…

Estimation of causal effects requires making comparisons across groups of observations exposed and not exposed to a a treatment or cause (intervention, program, drug, etc). To interpret differences between groups causally we need to ensure that they have been constructed in such a way that the comparisons are "fair." This can be…

Randomized A/B tests allow causal estimation without confounding but are often under-powered. This paper uses a new dataset, including over 250 randomized comparisons conducted in an online learning platform, to illustrate a method combining data from A/B tests with log data from users who were not in the experiment. Inference remains exact and…

A wide range of machine-learning-based approaches have been developed in the past decade, increasing our ability to accurately model nonlinear and nonadditive response surfaces. This has improved performance for inferential tasks such as estimating average treatment effects in situations where standard parametric models may not fit the data well.…

Emergent technologies present platforms for educational researchers to conduct randomized controlled trials (RCTs) and collect rich data on study students' performance, behavior, learning processes, and outcomes in authentic learning environments. As educational research increasingly uses methods and data collection from such platforms, it is…

Randomized control trials are considered the pinnacle for causal inference. In many cases, however, randomization of participants in social work research studies is not feasible or ethical. This paper introduces the co-twin control design study as an alternative quasi-experimental design to provide evidence of causal mechanisms when randomization…

With the growing attention on large-scale educational testing and assessment, the ability to process substantial volumes of response data becomes crucial. Current estimation methods within item response theory (IRT), despite their high precision, often pose considerable computational burdens with large-scale data, leading to reduced computational…

Multidimensional Item Response Theory (MIRT) is widely used in assessment and evaluation of educational and psychological tests. It models the individual response patterns by specifying functional relationship between individuals' multiple latent traits and their responses to test items. One major challenge in parameter estimation in MIRT is that…

Data science has maintained its popularity for about 20 years. This study adopts a bottom-up approach to understand what data science is by analyzing the descriptions of courses offered by the data science programs in the United States. Through topic modeling, 14 topics are identified from the current curricula of 56 data science programs. These…

We study a popular dual enrollment program in Washington State, "Running Start" using a new administrative database that links high school and postsecondary data. Conditional on prior high school performance, we find that students participating in Running Start are more likely to attend any college but less likely to attend four-year…